© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 27539
    Prev
    Next
    INDEX
    Explanations

    television series

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĬ½åıĸ
    -0.10
    åŁ¹è®ŃæľºæŀĦ
    -0.09
    UME
    -0.09
    æĹ¥å¸¸å·¥ä½ľ
    -0.09
    主åħ¬
    -0.09
    èĪľ
    -0.09
    å°Ķæĸ¯
    -0.09
    æ¹ĸåĮº
    -0.09
    funcs
    -0.09
    /OR
    -0.09
    POSITIVE LOGITS
    .biz
    0.09
    æıĸ
    0.09
     Markup
    0.08
    æŶéļĶ
    0.08
    è¯Ħä»·
    0.08
    å½ķ
    0.08
    LAS
    0.08
    eing
    0.07
     cohesion
    0.07
    ardon
    0.07
    Activations Density 0.166%

    No Known Activations